elevenlabs-stt

What problem does it solve?

Manual and time-consuming transcription of audio recordings is a bottleneck for meetings, podcasts, interviews, and voice notes; this Skill streamlines that work by producing accurate, time-aligned text and speaker-labeled transcripts automatically.

Core Features & Use Cases

• Multilingual transcription: Supports 90+ languages with automatic or explicit language selection for better accuracy.
• Speaker diarization & timestamps: Identifies different speakers and emits word-level timestamps for precise alignment.
• Audio event tagging & broad format support: Detects events like laughter or music and accepts common audio/video formats for podcast, meeting, and note workflows.
• Use Case: Turn a multi-speaker meeting recording into a JSON transcript with speaker labels and timestamps for downstream summarization, note-taking, or publishing.

Quick Start

Transcribe meeting.mp3 with diarization enabled and return the full JSON transcript including word-level timestamps and speaker labels.